
# filter warnings
import warnings
warnings.filterwarnings("ignore")
from statsmodels.tools.sm_exceptions import ConvergenceWarning

# import libraries for data manipulation
import pandas as pd
import numpy as np

# import libraries for data visualization
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

# import library to split data into train and test sets
from sklearn.model_selection import train_test_split

# import library to build model for prediction
import statsmodels.stats.api as sms
import statsmodels.api as sm
from statsmodels.tools.tools import add_constant
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

# import library to compute variance inflation factor
from statsmodels.stats.outliers_influence import variance_inflation_factor

# import library to tune models
from sklearn.model_selection import GridSearchCV

# import library to check model performance
from sklearn.metrics import (f1_score, accuracy_score, recall_score, precision_score, 
                             confusion_matrix, roc_auc_score, precision_recall_curve, roc_curve, make_scorer,)

# remove limit for displayed columns
pd.set_option('display.max_columns', None)

# set limit for displayed rows
pd.set_option('display.max_rows', 200)

# set floats to 5 decimal points
pd.set_option('display.float_format', lambda x: '%.5f' % x)


# mount google drive
from google.colab import drive
drive.mount('/content/drive')

# read the data set
df = pd.read_csv('/content/drive/MyDrive/Great Learning/Supervised Learning Classification/Project 4/INNHotelsGroup.csv')

Mounted at /content/drive


# return the first 5 rows
df.head()


# return the last 5 rows
df.tail()


# return the number of rows and columns
df.shape

(36275, 19)


# return a summary of the data
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 36275 entries, 0 to 36274
Data columns (total 19 columns):
 #   Column                                Non-Null Count  Dtype  
---  ------                                --------------  -----  
 0   Booking_ID                            36275 non-null  object 
 1   no_of_adults                          36275 non-null  int64  
 2   no_of_children                        36275 non-null  int64  
 3   no_of_weekend_nights                  36275 non-null  int64  
 4   no_of_week_nights                     36275 non-null  int64  
 5   type_of_meal_plan                     36275 non-null  object 
 6   required_car_parking_space            36275 non-null  int64  
 7   room_type_reserved                    36275 non-null  object 
 8   lead_time                             36275 non-null  int64  
 9   arrival_year                          36275 non-null  int64  
 10  arrival_month                         36275 non-null  int64  
 11  arrival_date                          36275 non-null  int64  
 12  market_segment_type                   36275 non-null  object 
 13  repeated_guest                        36275 non-null  int64  
 14  no_of_previous_cancellations          36275 non-null  int64  
 15  no_of_previous_bookings_not_canceled  36275 non-null  int64  
 16  avg_price_per_room                    36275 non-null  float64
 17  no_of_special_requests                36275 non-null  int64  
 18  booking_status                        36275 non-null  object 
dtypes: float64(1), int64(13), object(5)
memory usage: 5.3+ MB


# check for duplicate values 
df.duplicated().sum()

0


# check data for the count of null values (missing values) in each column
df.isnull().sum()

Booking_ID                              0
no_of_adults                            0
no_of_children                          0
no_of_weekend_nights                    0
no_of_week_nights                       0
type_of_meal_plan                       0
required_car_parking_space              0
room_type_reserved                      0
lead_time                               0
arrival_year                            0
arrival_month                           0
arrival_date                            0
market_segment_type                     0
repeated_guest                          0
no_of_previous_cancellations            0
no_of_previous_bookings_not_canceled    0
avg_price_per_room                      0
no_of_special_requests                  0
booking_status                          0
dtype: int64


# create a copy of the data so original data remains unchanged
data = df.copy()


# drop booking_id column
data = data.drop('Booking_ID', axis = 1)

# return the first 5 rows
data.head()


# describe the statistical summary of the categorical data
data.describe(include='object')


# describe the statistical summary of the numerical data
data.describe()


# define function to combine a boxplot and histogram into one figure
def histogram_boxplot(data, feature, figsize = (15, 11), kde = False, bins = None):

    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows = 2,  # (2) number of rows of the subplot grid
        sharex = True,  # share x axis among all subplots
        gridspec_kw = {'height_ratios': (0.25, 0.75)},
        figsize = figsize,) 
    
    # draw boxplot with mean
    sns.boxplot(
        data = data, x = feature, ax = ax_box2, showmeans = True, color= 'pink')
    
    # draw histrogram
    sns.histplot(
        data = data, x = feature, kde = kde, ax = ax_hist2, bins = bins) if bins else sns.histplot(
        data = data, x = feature, kde = kde, ax = ax_hist2)
    ax_hist2.axvline(
        data[feature].mean(), color = 'yellow', linestyle='--')  # show mean on histogram
    ax_hist2.axvline(
        data[feature].median(), color = 'black', linestyle='-')  # show median on histogram


# draw combined histogram and boxplot
histogram_boxplot(data, 'lead_time')

# label x axis
plt.xlabel('Lead Time');


# draw combined histogram and boxplot
histogram_boxplot(data, 'avg_price_per_room')

# label x axis
plt.xlabel('Average Price Per Room');


# check for values of 0 for avg_price_per_room
data[data['avg_price_per_room'] == 0]


# return counts for all rooms costing $0 broken down by market_segment_type
data.loc[data['avg_price_per_room'] == 0, 'market_segment_type'].value_counts()

Complementary    354
Online           191
Name: market_segment_type, dtype: int64


# calculate 25th quantile
Q1 = data['avg_price_per_room'].quantile(0.25)

# calculate 75th quantile
Q3 = data['avg_price_per_room'].quantile(0.75)

# calculate IQR
IQR = Q3 - Q1

# calculate upper whisker
upper_whisker = Q3 + 1.5 * IQR

upper_whisker

179.55


# assign outliers value of upper whisker
data.loc[data['avg_price_per_room'] >= 500, 'avg_price_per_room'] = upper_whisker


# redraw combined histogram and boxplot
histogram_boxplot(data, 'avg_price_per_room')

# label x axis
plt.xlabel('Average Price Per Room');


# draw combined histogram and boxplot
histogram_boxplot(data, 'no_of_previous_cancellations')

# label x axis
plt.xlabel('Number of Previous Cancellations');


# draw combined histogram and boxplot
histogram_boxplot(data, 'no_of_previous_bookings_not_canceled')

# label x axis
plt.xlabel('Number of Previous Bookings Not Canceled');


# define function to create labeled barplot
def labeled_barplot(data, feature, perc = False, n = None):

    total = len(data[feature])  # length of the column
    count = data[feature].nunique()
    if n is None:
        plt.figure(figsize = (count + 2, 6))
    else:
        plt.figure(figsize = (n + 2, 6))

    # rotate x labels 45 degrees and set font size
    plt.xticks(rotation = 45, fontsize = 15)
    ax = sns.countplot(data = data, x = feature, palette = 'Paired', order = data[feature].value_counts().index[:n],)

    for p in ax.patches:
        if perc == True:
            label = '{:.1f}%'.format(100 * p.get_height() / total)  # percentage of each class of category
        else:
            label = p.get_height()  # count of each level of category

        x = p.get_x() + p.get_width() / 2  # plot width
        y = p.get_height()  # plot height

        ax.annotate(
            label,
            (x, y), ha = 'center', va = 'center', size = 12, xytext = (0, 5), textcoords = 'offset points',)  # annotate percentage

    plt.show()


# draw labeled barplot
labeled_barplot(data, 'no_of_children', perc = True);


# replace 9 and 10 children with 3
data['no_of_children'] = data['no_of_children'].replace([9, 10], 3)


# redraw labeled barplot
labeled_barplot(data, 'no_of_children', perc = True);


# draw labeled barplot
labeled_barplot(data, 'no_of_adults', perc = True);


# draw labeled barplot
labeled_barplot(data, 'no_of_weekend_nights', perc = True);


# draw labeled barplot
labeled_barplot(data, 'no_of_week_nights', perc = True);


# draw labeled barplot
labeled_barplot(data, 'room_type_reserved', perc = True);


# draw labeled barplot
# 0 = no and 1 = yes
labeled_barplot(data, 'required_car_parking_space', perc = True);


# draw labeled barplot
labeled_barplot(data, 'type_of_meal_plan', perc = True);


# draw labeled barplot
labeled_barplot(data, 'arrival_month', perc = True);


# draw labeled barplot
labeled_barplot(data, 'market_segment_type', perc = True);


# draw labeled barplot
labeled_barplot(data, 'booking_status', perc = True);


# draw labeled barplot
labeled_barplot(data, 'no_of_special_requests', perc = True);


# draw correlation heatmap of numerical columns
cols = data.select_dtypes(include = np.number).columns.tolist()

# set figure size
plt.figure(figsize=(15, 10))

# draw heatmap
sns.heatmap(data[cols].corr(), annot = True, vmin = -1, vmax = 1, fmt = '.2f', cmap = 'Spectral');

# rotate x labels 45 degrees and set font size to 10
plt.xticks(rotation = 45, fontsize = 10);


# create function to plot distributions with respect to target
# used to identify potential patterns and relationships 
def wrt_target(data, predictor, target):

    fig, axs = plt.subplots(2, 2, figsize = (12, 10))

    target_uniq = data[target].unique()

    axs[0, 0].set_title('Distribution of Target for Target = ' + str(target_uniq[0]))
    
    # draw histplot
    sns.histplot(data = data[data[target] == target_uniq[0]],
        x = predictor, kde = True, ax = axs[0, 0], color = 'teal', stat = 'density',)

    axs[0, 1].set_title('Distribution of Target for Target =' + str(target_uniq[1]))
    
    # draw histplot
    sns.histplot(data = data[data[target] == target_uniq[1]],
        x = predictor, kde = True, ax = axs[0, 1], color = 'orange', stat = 'density',)

    axs[1, 0].set_title('Boxplot W.R.T Target')
    
    # draw boxplot
    sns.boxplot(data = data, x = target, y = predictor, ax = axs[1, 0], palette = 'gist_rainbow')

    axs[1, 1].set_title('Boxplot (without outliers) W.R.T Target')
   
   # draw boxplot
    sns.boxplot(data = data, x = target, y = predictor, ax = axs[1, 1], showfliers = False, palette = 'gist_rainbow',)

    plt.tight_layout()
    plt.show()


# create function to draw stacked barplots
# good for showing how the composition of a group changes across categories
def stacked_barplot(data, predictor, target):
   
    count = data[predictor].nunique()
    sorter = data[target].value_counts().index[-1]
    tab1 = pd.crosstab(data[predictor], data[target], margins = True).sort_values(by = sorter, ascending = False)
    print(tab1)
    print('-' * 120)
    tab = pd.crosstab(data[predictor], data[target], normalize = 'index').sort_values(by = sorter, ascending = False)
    tab.plot(kind='bar', stacked=True, figsize=(count + 5, 5))
    
    # show legend
    plt.legend(loc = 'lower left', frameon = False,)
    plt.legend(loc = 'upper left', bbox_to_anchor = (1, 1))
    
    plt.show()


# group data by arrival month and extract count
monthly_data = data.groupby(['arrival_month'])['booking_status'].count()

# create dataframe with months and count
monthly_data = pd.DataFrame(
    {'Month': list(monthly_data.index), 'Guests': list(monthly_data.values)})

# set figure size
plt.figure(figsize = (10, 5))

# draw a lineplot to plot the trend
sns.lineplot(data = monthly_data, x='Month', y = 'Guests');


# draw labeled barplot
labeled_barplot(data, 'market_segment_type', perc = True)


# set figure size
plt.figure(figsize=(15, 8))

# draw boxplot
sns.boxplot(data = data, x = 'market_segment_type', y = 'avg_price_per_room', palette ='gist_rainbow');


# encode canceled bookings as 1 and not canceled bookings as 0
data['booking_status'] = data['booking_status'].apply(lambda x: 1 if x == 'Canceled' else 0)


# draw stacked barplot
# canceled bookings = 1 and not canceled bookings = 0
stacked_barplot(data, 'market_segment_type', 'booking_status')

booking_status           0      1    All
market_segment_type                     
All                  24390  11885  36275
Online               14739   8475  23214
Offline               7375   3153  10528
Corporate             1797    220   2017
Aviation                88     37    125
Complementary          391      0    391
------------------------------------------------------------------------------------------------------------------------


# draw stacked barplot
# canceled bookings = 1 and not canceled bookings = 0
stacked_barplot(data, 'arrival_month', 'booking_status')

booking_status      0      1    All
arrival_month                      
All             24390  11885  36275
10               3437   1880   5317
9                3073   1538   4611
8                2325   1488   3813
7                1606   1314   2920
6                1912   1291   3203
4                1741    995   2736
5                1650    948   2598
11               2105    875   2980
3                1658    700   2358
2                1274    430   1704
12               2619    402   3021
1                 990     24   1014
------------------------------------------------------------------------------------------------------------------------


# print percentage of booking canceled
print((11885 / 36275) * 100)

32.76361130254997


# draw stacked barplot
# canceled bookings = 1 and not canceled bookings = 0
# repeat guest yes = 1 and repeat guest no = 0
stacked_barplot(data, 'repeated_guest', 'booking_status')

booking_status      0      1    All
repeated_guest                     
All             24390  11885  36275
0               23476  11869  35345
1                 914     16    930
------------------------------------------------------------------------------------------------------------------------


# print percentage of repeat guests that cancel
print((16 / 930) * 100)

1.7204301075268817


# print percentage of guests that are repeat guests
print((930 / 36275) * 100)

2.563749138525155


# draw stacked barplot
# canceled bookings = 1 and not canceled bookings = 0
stacked_barplot(data, 'no_of_special_requests', 'booking_status')

booking_status              0      1    All
no_of_special_requests                     
All                     24390  11885  36275
0                       11232   8545  19777
1                        8670   2703  11373
2                        3727    637   4364
3                         675      0    675
4                          78      0     78
5                           8      0      8
------------------------------------------------------------------------------------------------------------------------


# set figure size
plt.figure(figsize=(15, 10))

# draw boxplot
sns.boxplot(data, x = 'no_of_special_requests', y = 'avg_price_per_room');


# draw with respect to target plots
# canceled bookings = 1 and not canceled bookings = 0
wrt_target(data, 'avg_price_per_room', 'booking_status')


# draw with repsect to target plots
# canceled bookings = 1 and not canceled bookings = 0
wrt_target(data, 'lead_time', 'booking_status')


# group data on arrival month and extract booking count
monthly_data = data.groupby(['arrival_month'])['booking_status'].count()

# create data frame with months and count
monthly_data = pd.DataFrame({'Month': list(monthly_data.index), 'Guests': list(monthly_data.values)})

# set figure size
plt.figure(figsize=(15, 10))

# plot the trend over different months
sns.lineplot(data = monthly_data, x = 'Month', y = 'Guests');


# set figure size
plt.figure(figsize = (15, 10))

# draw lineplot
sns.lineplot(data, x = 'arrival_month', y = 'avg_price_per_room');


# outlier detection using boxplot
numeric_columns = data.select_dtypes(include=np.number).columns.tolist()

# drop booking_status
numeric_columns.remove('booking_status')

plt.figure(figsize=(15, 12))

for i, variable in enumerate(numeric_columns):
    plt.subplot(4, 4, i + 1)
    plt.boxplot(data[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()


# define function to compute metrics to check performance of classification model using statsmodels
def model_performance_classification_statsmodels(
    model, predictors, target, threshold=0.5
):
    # check which probabilities are greater than threshold
    pred_temp = model.predict(predictors) > threshold

    # round off above values to get classes
    pred = np.round(pred_temp)

    # compute accuracy
    acc = accuracy_score(target, pred)

    # compute recall
    recall = recall_score(target, pred)

    # compute precision
    precision = precision_score(target, pred)

    # compute F1-score
    f1 = f1_score(target, pred)

    # create dataframe of metrics
    df_perf = pd.DataFrame(
        {'Accuracy': acc, 'Recall': recall, 'Precision': precision, 'F1': f1,}, index=[0],)

    return df_perf


# define function to plot confusion_matrix of classification model

def confusion_matrix_statsmodels(model, predictors, target, threshold = 0.5):
 
    y_pred = model.predict(predictors) > threshold
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ['{0:0.0f}'.format(item) + '\n{0:.2%}'.format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    # set figure size 
    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")

    # set labels
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')


# define dependent and independent variables
X = data.drop(['booking_status'], axis = 1)
y = data['booking_status']

# add constant
X = sm.add_constant(X)

# create dummy variables
X = pd.get_dummies(X, drop_first = True)
X.head()


# split data using 70:30 ratio for train to test data (70:30 is most common split ratio, 70% knowledge goes to training set and 30% knowledge goes to test set)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 1)


# check the number of rows in each set
print('The number of rows in the train data set = ', X_train.shape[0])
print('The number of rows in the test data set = ', X_test.shape[0])

The number of rows in the train data set =  25392
The number of rows in the test data set =  10883


# canceled bookings = 1 and not canceled bookings = 0
# print percentage of each class in the training set
print('Percentage of classes in training set:')
print(y_train.value_counts(normalize=True))

# print percentage of each class in the test set
print('Percentage of classes in test set:')
print(y_test.value_counts(normalize=True))

Percentage of classes in training set:
0   0.67064
1   0.32936
Name: booking_status, dtype: float64
Percentage of classes in test set:
0   0.67638
1   0.32362
Name: booking_status, dtype: float64


# draw combined histogram and boxplot
histogram_boxplot(data, 'lead_time')

# label x axis
plt.xlabel('Lead Time');


# draw combined histogram and boxplot
histogram_boxplot(data, 'avg_price_per_room')

# label x axis
plt.xlabel('Average Price Per Room');


# draw combined histogram and boxplot
histogram_boxplot(data, 'no_of_previous_cancellations')

# label x axis
plt.xlabel('Number of Previous Cancellations');


# draw combined histogram and boxplot
histogram_boxplot(data, 'no_of_previous_bookings_not_canceled')

# label x axis
plt.xlabel('Number of Previous Bookings Not Canceled');


# fitting logistic regression model
logit = sm.Logit(y_train, X_train.astype(float))

lg = logit.fit(disp = False) 

print(lg.summary())

/usr/local/lib/python3.9/dist-packages/statsmodels/base/model.py:604: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals
  warnings.warn("Maximum Likelihood optimization failed to "

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25364
Method:                           MLE   Df Model:                           27
Date:                Wed, 05 Apr 2023   Pseudo R-squ.:                  0.3292
Time:                        17:30:32   Log-Likelihood:                -10794.
converged:                      False   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -922.8266    120.832     -7.637      0.000   -1159.653    -686.000
no_of_adults                             0.1137      0.038      3.019      0.003       0.040       0.188
no_of_children                           0.1580      0.062      2.544      0.011       0.036       0.280
no_of_weekend_nights                     0.1067      0.020      5.395      0.000       0.068       0.145
no_of_week_nights                        0.0397      0.012      3.235      0.001       0.016       0.064
required_car_parking_space              -1.5943      0.138    -11.565      0.000      -1.865      -1.324
lead_time                                0.0157      0.000     58.863      0.000       0.015       0.016
arrival_year                             0.4561      0.060      7.617      0.000       0.339       0.573
arrival_month                           -0.0417      0.006     -6.441      0.000      -0.054      -0.029
arrival_date                             0.0005      0.002      0.259      0.796      -0.003       0.004
repeated_guest                          -2.3472      0.617     -3.806      0.000      -3.556      -1.139
no_of_previous_cancellations             0.2664      0.086      3.108      0.002       0.098       0.434
no_of_previous_bookings_not_canceled    -0.1727      0.153     -1.131      0.258      -0.472       0.127
avg_price_per_room                       0.0188      0.001     25.396      0.000       0.017       0.020
no_of_special_requests                  -1.4689      0.030    -48.782      0.000      -1.528      -1.410
type_of_meal_plan_Meal Plan 2            0.1756      0.067      2.636      0.008       0.045       0.306
type_of_meal_plan_Meal Plan 3           17.3584   3987.836      0.004      0.997   -7798.656    7833.373
type_of_meal_plan_Not Selected           0.2784      0.053      5.247      0.000       0.174       0.382
room_type_reserved_Room_Type 2          -0.3605      0.131     -2.748      0.006      -0.618      -0.103
room_type_reserved_Room_Type 3          -0.0012      1.310     -0.001      0.999      -2.568       2.566
room_type_reserved_Room_Type 4          -0.2823      0.053     -5.304      0.000      -0.387      -0.178
room_type_reserved_Room_Type 5          -0.7189      0.209     -3.438      0.001      -1.129      -0.309
room_type_reserved_Room_Type 6          -0.9501      0.151     -6.274      0.000      -1.247      -0.653
room_type_reserved_Room_Type 7          -1.4003      0.294     -4.770      0.000      -1.976      -0.825
market_segment_type_Complementary      -40.5975   5.65e+05  -7.19e-05      1.000   -1.11e+06    1.11e+06
market_segment_type_Corporate           -1.1924      0.266     -4.483      0.000      -1.714      -0.671
market_segment_type_Offline             -2.1946      0.255     -8.621      0.000      -2.694      -1.696
market_segment_type_Online              -0.3995      0.251     -1.590      0.112      -0.892       0.093
========================================================================================================


# check model performance on train set

print('Performance of Train Set:')
model_performance_classification_statsmodels(lg, X_train, y_train)

Performance of Train Set:


# define function to check variance inflation factor
def checking_vif(predictors):
    vif = pd.DataFrame()
    vif['feature'] = predictors.columns

    # calculate VIF for each feature
    vif['VIF'] = [
        variance_inflation_factor(predictors.values, i)
        for i in range(len(predictors.columns))]
        
    return vif


# call function on train set
checking_vif(X_train)


# initial list of columns
cols = X_train.columns.tolist()

# setting an initial max p-value
max_p_value = 1

while len(cols) > 0:
    # defining the train set
    x_train_aux = X_train[cols]

    # fitting the model
    model = sm.Logit(y_train, x_train_aux).fit(disp=False)

    # getting the p-values and the maximum p-value
    p_values = model.pvalues
    max_p_value = max(p_values)

    # name of the variable with maximum p-value
    feature_with_p_max = p_values.idxmax()

    if max_p_value > 0.05:
        cols.remove(feature_with_p_max)
    else:
        break

selected_features = cols
print(selected_features)

/usr/local/lib/python3.9/dist-packages/statsmodels/base/model.py:604: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals
  warnings.warn("Maximum Likelihood optimization failed to "

['const', 'no_of_adults', 'no_of_children', 'no_of_weekend_nights', 'no_of_week_nights', 'required_car_parking_space', 'lead_time', 'arrival_year', 'arrival_month', 'repeated_guest', 'no_of_previous_cancellations', 'avg_price_per_room', 'no_of_special_requests', 'type_of_meal_plan_Meal Plan 2', 'type_of_meal_plan_Not Selected', 'room_type_reserved_Room_Type 2', 'room_type_reserved_Room_Type 4', 'room_type_reserved_Room_Type 5', 'room_type_reserved_Room_Type 6', 'room_type_reserved_Room_Type 7', 'market_segment_type_Corporate', 'market_segment_type_Offline']


# create new train set with selected features
X_train1 = X_train[selected_features]
X_test1 = X_test[selected_features]


# train logistic regression on new train1
logit1 = sm.Logit(y_train, X_train1.astype(float))

lg1 = logit1.fit(disp=False)

print(lg1.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25370
Method:                           MLE   Df Model:                           21
Date:                Wed, 05 Apr 2023   Pseudo R-squ.:                  0.3282
Time:                        17:30:37   Log-Likelihood:                -10810.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
==================================================================================================
                                     coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------
const                           -915.6391    120.471     -7.600      0.000   -1151.758    -679.520
no_of_adults                       0.1088      0.037      2.914      0.004       0.036       0.182
no_of_children                     0.1531      0.062      2.470      0.014       0.032       0.275
no_of_weekend_nights               0.1086      0.020      5.498      0.000       0.070       0.147
no_of_week_nights                  0.0417      0.012      3.399      0.001       0.018       0.066
required_car_parking_space        -1.5947      0.138    -11.564      0.000      -1.865      -1.324
lead_time                          0.0157      0.000     59.213      0.000       0.015       0.016
arrival_year                       0.4523      0.060      7.576      0.000       0.335       0.569
arrival_month                     -0.0425      0.006     -6.591      0.000      -0.055      -0.030
repeated_guest                    -2.7367      0.557     -4.916      0.000      -3.828      -1.646
no_of_previous_cancellations       0.2288      0.077      2.983      0.003       0.078       0.379
avg_price_per_room                 0.0192      0.001     26.336      0.000       0.018       0.021
no_of_special_requests            -1.4698      0.030    -48.884      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2      0.1642      0.067      2.469      0.014       0.034       0.295
type_of_meal_plan_Not Selected     0.2860      0.053      5.406      0.000       0.182       0.390
room_type_reserved_Room_Type 2    -0.3552      0.131     -2.709      0.007      -0.612      -0.098
room_type_reserved_Room_Type 4    -0.2828      0.053     -5.330      0.000      -0.387      -0.179
room_type_reserved_Room_Type 5    -0.7364      0.208     -3.535      0.000      -1.145      -0.328
room_type_reserved_Room_Type 6    -0.9682      0.151     -6.403      0.000      -1.265      -0.672
room_type_reserved_Room_Type 7    -1.4343      0.293     -4.892      0.000      -2.009      -0.860
market_segment_type_Corporate     -0.7913      0.103     -7.692      0.000      -0.993      -0.590
market_segment_type_Offline       -1.7854      0.052    -34.363      0.000      -1.887      -1.684
==================================================================================================


# check model performance on train set

print('Performance of Train Set:')
model_performance_classification_statsmodels(lg1,X_train1, y_train)

Performance of Train Set:


# convert coefficients to odds
odds = np.exp(lg1.params)

# find percentage change
perc_change_odds = (np.exp(lg1.params) - 1) * 100

# remove limit from number of columns to display
pd.set_option('display.max_columns', None)

# add odds to dataframe
pd.DataFrame({'Odds': odds, 'Change_odd%': perc_change_odds}, index=X_train1.columns).T


# create confusion matrix
confusion_matrix_statsmodels(lg1, X_train1, y_train)


# check model performance on train set
print('Performance of Train Set:')

log_reg_model_train_perf = model_performance_classification_statsmodels(lg1, X_train1, y_train)

log_reg_model_train_perf

Performance of Train Set:


logit_roc_auc_train = roc_auc_score(y_train, lg1.predict(X_train1))
fpr, tpr, thresholds = roc_curve(y_train, lg1.predict(X_train1))

# set figure size
plt.figure(figsize=(7, 5))

plt.plot(fpr, tpr, label= 'Logistic Regression (area = %0.2f)' % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.01])

# set labels and title 
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')

# move legend 
plt.legend(loc='lower right')

plt.show()


# calculate optimal threshold valye for model base on ROC curve
# optimal cut off = high tpr and low fpr 
fpr, tpr, thresholds = roc_curve(y_train, lg1.predict(X_train1))

optimal_idx = np.argmax(tpr - fpr)

optimal_threshold_auc_roc = thresholds[optimal_idx]

print(optimal_threshold_auc_roc)

0.3700522558708252


# create confusion matrix
confusion_matrix_statsmodels(
    lg1, X_train1, y_train, threshold=optimal_threshold_auc_roc)


# check model performance
log_reg_model_train_perf_threshold_auc_roc = model_performance_classification_statsmodels(
    lg1, X_train1, y_train, threshold=optimal_threshold_auc_roc)

# check model performance on train set
print('Performance of Train Set:')
log_reg_model_train_perf_threshold_auc_roc

Performance of Train Set:


y_scores = lg1.predict(X_train1)
prec, rec, tre = precision_recall_curve(y_train, y_scores,)

# define function for plot
def plot_prec_recall_vs_tresh(precisions, recalls, thresholds):
    plt.plot(thresholds, precisions[:-1], 'b--', label='precision')
    plt.plot(thresholds, recalls[:-1], 'g--', label='recall')
    
    # set label
    plt.xlabel('Threshold')

    # move legend
    plt.legend(loc = 'upper left')
    plt.ylim([0, 1])

# set figure size
plt.figure(figsize=(10, 7))

plot_prec_recall_vs_tresh(prec, rec, tre)

plt.show()


# set threshold
optimal_threshold_curve = 0.42


# create confusion matrix
confusion_matrix_statsmodels(
    lg1, X_train1, y_train, threshold=optimal_threshold_curve)


# check model performance
log_reg_model_train_perf_threshold_curve = model_performance_classification_statsmodels(
    lg1, X_train1, y_train, threshold=optimal_threshold_curve)

# check model performance on train set
print('Performance of Train Set:')
log_reg_model_train_perf_threshold_curve

Performance of Train Set:


# create confusion matrix
confusion_matrix_statsmodels(lg1, X_test1, y_test, threshold=optimal_threshold_curve)


# check model performance
log_reg_model_test_perf_threshold_curve = model_performance_classification_statsmodels(lg1, X_test1, y_test, threshold=optimal_threshold_curve)

# check model performance on test set
print('Performance of Test Set:')
log_reg_model_test_perf_threshold_curve

Performance of Test Set:


logit_roc_auc_train = roc_auc_score(y_test, lg1.predict(X_test1))
fpr, tpr, thresholds = roc_curve(y_test, lg1.predict(X_test1))

# set figure size
plt.figure(figsize=(7, 5))

# draw plot
plt.plot(fpr, tpr, label = 'Logistic Regression (area = %0.2f)' % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], 'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.01])

# set labels and title
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')

# move legend
plt.legend(loc='lower right')

plt.show()


# create confusion matrix
confusion_matrix_statsmodels(lg1, X_test1, y_test, threshold = optimal_threshold_auc_roc)


# check model performance
log_reg_model_test_perf_threshold_auc_roc1 = model_performance_classification_statsmodels(
    lg1, X_test1, y_test, threshold= optimal_threshold_auc_roc)

# check model performance on test set
print('Performance of Test Set:')
log_reg_model_test_perf_threshold_auc_roc1

Performance of Test Set:


# create confusion matrix
confusion_matrix_statsmodels(lg1, X_test1, y_test, threshold = optimal_threshold_curve)


# check model perfomance
log_reg_model_test_perf_threshold_curve2 = model_performance_classification_statsmodels(
    lg1, X_test1, y_test, threshold=optimal_threshold_curve)

# check model performance on test set
print('Performance of Test Set:')
log_reg_model_test_perf_threshold_curve2

Performance of Test Set:


# compare training performances

models_train_comp_df = pd.concat(
    [
        log_reg_model_train_perf.T,
        log_reg_model_train_perf_threshold_auc_roc.T,
        log_reg_model_train_perf_threshold_curve.T,
    ],
    axis = 1,
)
models_train_comp_df.columns = [
    'Logistic Regression-default Threshold',
    'Logistic Regression-0.37 Threshold',
    'Logistic Regression-0.42 Threshold',
]

print('Training Performance Comparison:')
models_train_comp_df

Training Performance Comparison:


# compare testing performance

models_test_comp_df = pd.concat(
    [
        log_reg_model_test_perf_threshold_curve.T,
        log_reg_model_test_perf_threshold_auc_roc1.T,
        log_reg_model_test_perf_threshold_curve2.T,
    ],
    axis = 1,
)
models_test_comp_df.columns = [
    'Logistic Regression-default Threshold',
    'Logistic Regression-0.37 Threshold',
    'Logistic Regression-0.42 Threshold',
]

print('Testing Performance Comparison:')
models_test_comp_df

Testing Performance Comparison:


X = data.drop(['booking_status'], axis=1)
Y = data['booking_status']

# encode categorical variables
X = pd.get_dummies(X, drop_first = True)

# splitting data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state=1)

X.head()


print("Shape of Training set : ", X_train.shape)
print("Shape of test set : ", X_test.shape)
print("Percentage of classes in training set:")
print(y_train.value_counts(normalize=True))
print("Percentage of classes in test set:")
print(y_test.value_counts(normalize=True))

Shape of Training set :  (25392, 27)
Shape of test set :  (10883, 27)
Percentage of classes in training set:
0   0.67064
1   0.32936
Name: booking_status, dtype: float64
Percentage of classes in test set:
0   0.67638
1   0.32362
Name: booking_status, dtype: float64


# define function to compute metrics to check performance of classification model using sklearn
def model_performance_classification_sklearn(model, predictors, target):
  
    # predict using independent variables
    pred = model.predict(predictors)

    # computer accuracy
    acc = accuracy_score(target, pred)

    # compute recall
    recall = recall_score(target, pred)

    # compute precision
    precision = precision_score(target, pred)

    # compute F1-scoree
    f1 = f1_score(target, pred)

    # create dataframe of metrics
    df_perf = pd.DataFrame(
        {'Accuracy': acc, 'Recall': recall, 'Precision': precision, 'F1': f1,}, index=[0],)

    return df_perf


# define function to plot confusion matrix with percentages
def confusion_matrix_sklearn(model, predictors, target):

    y_pred = model.predict(predictors)
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [['{0:0.0f}'.format(item) + '\n{0:.2%}'.format(item / cm.flatten().sum())]
            for item in cm.flatten()]).reshape(2, 2)

    # set figure size
    plt.figure(figsize=(6, 4))

    # draw heatmap
    sns.heatmap(cm, annot=labels, fmt="")

    # set labels
    plt.ylabel('True label')
    plt.xlabel('Predicted label')


# fit decision tree on train data
model = DecisionTreeClassifier(random_state = 1)
model.fit(X_train, y_train)

DecisionTreeClassifier(random_state=1)

DecisionTreeClassifier(random_state=1)


# plot confusion matrix
confusion_matrix_sklearn(model, X_train, y_train)


decision_tree_perf_train = model_performance_classification_sklearn(
    model, X_train, y_train)
decision_tree_perf_train


# plot confusion matrix
confusion_matrix_sklearn(model, X_test, y_test)


decision_tree_perf_test = model_performance_classification_sklearn(
    model, X_test, y_test)
decision_tree_perf_test


# extract feature names from training data set
feature_names = list(X_train.columns)

# get feature importances from the model
importances = model.feature_importances_

# sort the feature importances in ascending order
indices = np.argsort(importances)

# set figure size
plt.figure(figsize=(8, 8))

# set title and labels
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color = 'violet', align = 'center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance')

plt.show()


# choose classifier type
estimator = DecisionTreeClassifier(random_state = 1)

# parameters
parameters = {
    'class_weight': [None, 'balanced'],
    'max_depth': np.arange(2, 7, 2),
    'max_leaf_nodes': [50, 75, 150, 250],
    'min_samples_split': [10, 30, 50, 70],}

# score type
acc_scorer = make_scorer(f1_score)

# run grid search
grid_obj = GridSearchCV(estimator, parameters, scoring = acc_scorer, cv = 5)
grid_obj = grid_obj.fit(X_train, y_train)

# set clf to best combination of parameters
estimator = grid_obj.best_estimator_

# fit best algorithm
estimator.fit(X_train, y_train)

DecisionTreeClassifier(class_weight='balanced', max_depth=6, max_leaf_nodes=50,
                       min_samples_split=10, random_state=1)

DecisionTreeClassifier(class_weight='balanced', max_depth=6, max_leaf_nodes=50,
                       min_samples_split=10, random_state=1)


decision_tree_tune_perf_train = model_performance_classification_sklearn(
    estimator, X_train, y_train)

decision_tree_tune_perf_train


# plot confusion matrix 
confusion_matrix_sklearn(estimator, X_train, y_train)


decision_tree_tune_perf_test = model_performance_classification_sklearn(
    estimator, X_test, y_test)

decision_tree_tune_perf_test


# plot confusion matrix
confusion_matrix_sklearn(estimator, X_test, y_test)


# draw tree plot
plt.figure(figsize = (20, 10))
out = tree.plot_tree(
    estimator,
    feature_names = feature_names,
    filled = True,
    fontsize = 9,
    node_ids = False,
    class_names = None,)

plt.show()


# ouput report showing the rules of decision tree
print(tree.export_text(estimator, feature_names = feature_names, show_weights = True))

|--- lead_time <= 151.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 196.50
|   |   |   |   |   |   |--- weights: [1736.39, 133.59] class: 0
|   |   |   |   |   |--- avg_price_per_room >  196.50
|   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |--- weights: [960.27, 223.16] class: 0
|   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |--- weights: [129.73, 160.92] class: 1
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- lead_time <= 117.50
|   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |--- weights: [214.72, 227.72] class: 1
|   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |--- weights: [82.76, 285.41] class: 1
|   |   |   |   |--- lead_time >  117.50
|   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |--- weights: [87.23, 81.98] class: 0
|   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |--- weights: [228.14, 48.58] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 13.50
|   |   |   |   |--- avg_price_per_room <= 99.44
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [92.45, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- weights: [363.83, 132.08] class: 0
|   |   |   |   |--- avg_price_per_room >  99.44
|   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |--- weights: [219.94, 85.01] class: 0
|   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |--- weights: [132.71, 280.85] class: 1
|   |   |   |--- lead_time >  13.50
|   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 71.92
|   |   |   |   |   |   |--- weights: [158.80, 159.40] class: 1
|   |   |   |   |   |--- avg_price_per_room >  71.92
|   |   |   |   |   |   |--- weights: [850.67, 3543.28] class: 1
|   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |--- weights: [48.46, 1.52] class: 0
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |--- lead_time <= 102.50
|   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |--- weights: [697.09, 9.11] class: 0
|   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |--- weights: [15.66, 9.11] class: 0
|   |   |   |   |--- lead_time >  102.50
|   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |--- weights: [32.06, 19.74] class: 0
|   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |--- weights: [44.73, 3.04] class: 0
|   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |--- lead_time <= 8.50
|   |   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |   |--- weights: [498.03, 44.03] class: 0
|   |   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |   |--- weights: [258.71, 63.76] class: 0
|   |   |   |   |--- lead_time >  8.50
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- weights: [2512.51, 1451.32] class: 0
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.20, 1.52] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- weights: [1585.04, 0.00] class: 0
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [180.42, 57.69] class: 0
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [52.19, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |--- weights: [184.90, 56.17] class: 0
|   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |--- weights: [106.61, 106.27] class: 0
|   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |--- weights: [67.10, 0.00] class: 0
|--- lead_time >  151.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- no_of_special_requests <= 0.50
|   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |--- lead_time <= 163.50
|   |   |   |   |   |   |--- weights: [3.73, 24.29] class: 1
|   |   |   |   |   |--- lead_time >  163.50
|   |   |   |   |   |   |--- weights: [257.96, 62.24] class: 0
|   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |--- avg_price_per_room <= 2.50
|   |   |   |   |   |   |--- weights: [8.95, 3.04] class: 0
|   |   |   |   |   |--- avg_price_per_room >  2.50
|   |   |   |   |   |   |--- weights: [0.75, 97.16] class: 1
|   |   |   |--- no_of_adults >  1.50
|   |   |   |   |--- avg_price_per_room <= 82.47
|   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |--- weights: [2.98, 282.37] class: 1
|   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |--- weights: [213.97, 385.60] class: 1
|   |   |   |   |--- avg_price_per_room >  82.47
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- weights: [23.86, 1030.80] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |--- no_of_special_requests >  0.50
|   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |--- weights: [7.46, 7.59] class: 1
|   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |--- weights: [37.28, 4.55] class: 0
|   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [20.13, 212.54] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- weights: [231.12, 110.82] class: 0
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- weights: [19.38, 34.92] class: 1
|   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |--- lead_time <= 348.50
|   |   |   |   |   |   |--- weights: [106.61, 3.04] class: 0
|   |   |   |   |   |--- lead_time >  348.50
|   |   |   |   |   |   |--- weights: [5.96, 4.55] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- arrival_month <= 11.50
|   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |--- weights: [0.00, 3200.19] class: 1
|   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |--- arrival_month >  11.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- weights: [35.04, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |--- weights: [3.73, 22.77] class: 1


# importance features

importances = estimator.feature_importances_
indices = np.argsort(importances)

# plot figure
plt.figure(figsize = (10, 10))
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color = 'violet', align = 'center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance')

plt.show()


# initialize DecisionTreeClassifier object with random state 1 and class weight balanced
clf = DecisionTreeClassifier(random_state=1, class_weight='balanced')

# determine path of cost complexity pruning for training data
path = clf.cost_complexity_pruning_path(X_train, y_train)

# extract effective alphas for pruning and impurities at the effective alphas
ccp_alphas, impurities = abs(path.ccp_alphas), path.impurities


pd.DataFrame(path)


fig, ax = plt.subplots(figsize = (10, 5))

ax.plot(ccp_alphas[:-1], impurities[:-1], marker = 'o', drawstyle = 'steps-post')
ax.set_xlabel('Effective Alpha')
ax.set_ylabel('Total Impurity of Leaves')
ax.set_title('Total Impurity vs Effective Alpha for Training Set')

plt.show()


# create empty list to store decision tree classifiers
clfs = []

# loop through different values of ccp_alpha
for ccp_alpha in ccp_alphas:

    # instantiate a DecisionTreeClassifier object with specified parameters
    clf = DecisionTreeClassifier(
        random_state=1, ccp_alpha=ccp_alpha, class_weight='balanced')
   
    # train classifier on training data
    clf.fit(X_train, y_train)
    
    # add trained classifier to the list
    clfs.append(clf)

# print the number of nodes in the last tree and the corresponding value of ccp_alpha
print('The number of nodes in the last tree is: {} with ccp_alpha: {}'.format(
        clfs[-1].tree_.node_count, ccp_alphas[-1]))

The number of nodes in the last tree is: 1 with ccp_alpha: 0.0811791438913696


# remove the last classifier and corresponding ccp_alpha from the list and array
clfs = clfs[:-1]
ccp_alphas = ccp_alphas[:-1]

# get number of nodes and depth of each tree in list of classifiers
node_counts = [clf.tree_.node_count for clf in clfs]
depth = [clf.tree_.max_depth for clf in clfs]

# create plot with two subplots to show relationship between alpha and number of nodes/depth of tree
fig, ax = plt.subplots(2, 1, figsize=(10, 7))

# plot number of nodes vs alpha on first subplot
ax[0].plot(ccp_alphas, node_counts, marker='o', drawstyle='steps-post')
ax[0].set_xlabel('Alpha')
ax[0].set_ylabel('Number of Nodes')
ax[0].set_title('Number of Nodes vs Alpha')

# plot the depth of tree vs alpha on the second subplot
ax[1].plot(ccp_alphas, depth, marker="o", drawstyle='steps-post')
ax[1].set_xlabel('Alpha')
ax[1].set_ylabel('Depth of Tree')
ax[1].set_title('Depth vs Alpha')

# adjust the layout of the plot for better spacing
fig.tight_layout()


# create empty list to store f1-score for training set
f1_train = []

# loop over list of trained decision trees
for clf in clfs:
    
    # make predictions on training set using current decision tree
    pred_train = clf.predict(X_train)
   
    # compute f1-score for training set predictions
    values_train = f1_score(y_train, pred_train)

    # append f1-score to list
    f1_train.append(values_train)

# create empty list to store f1-score for test set
f1_test = []

# loop over list of trained decision trees
for clf in clfs:

    # make predictions on test set using current decision tree
    pred_test = clf.predict(X_test)

    # compute f1-score for test set predictions
    values_test = f1_score(y_test, pred_test)

    # append f1-score to list
    f1_test.append(values_test)


# create plot with figure size 15x5
fig, ax = plt.subplots(figsize=(15, 5))

# set labels and title
ax.set_xlabel('Alpha')
ax.set_ylabel('F1-Score')
ax.set_title('F1-Score vs Alpha for Training and Testing Sets')

# plot F1-score against the alpha values for both training and testing sets
ax.plot(ccp_alphas, f1_train, marker='o', label='Train', drawstyle='steps-post')
ax.plot(ccp_alphas, f1_test, marker='o', label='Test', drawstyle='steps-post')

# add legend
ax.legend()

plt.show()


# find index of model with highest F1-score on test set
index_best_model = np.argmax(f1_test) 

# select best model based on index found above
best_model = clfs[index_best_model] 

# print details of best model
print(best_model)

DecisionTreeClassifier(ccp_alpha=0.00012267633155167043,
                       class_weight='balanced', random_state=1)


# plot confusion matrix
confusion_matrix_sklearn(best_model, X_train, y_train)


decision_tree_post_perf_train = model_performance_classification_sklearn(
    best_model, X_train, y_train)

decision_tree_post_perf_train


# plot confusion matrix
confusion_matrix_sklearn(best_model, X_test, y_test)


decision_tree_post_test = model_performance_classification_sklearn(
    best_model, X_test, y_test
)
decision_tree_post_test


# set figure size
plt.figure(figsize=(20, 10))

# plot decision tree using best model with parameters
out = tree.plot_tree(
    best_model,
    feature_names=feature_names,  # names of the features
    filled=True,  # fill nodes with colors
    fontsize=9,  # set font size
    node_ids=False,  # do not display node IDs
    class_names=None,  # so not display class names
)

plt.show()


# output report showing rules of decision tree

print(tree.export_text(best_model, feature_names=feature_names, show_weights=True))

|--- lead_time <= 151.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 196.50
|   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |--- lead_time <= 16.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 68.50
|   |   |   |   |   |   |   |   |   |--- weights: [207.26, 10.63] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  68.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 29.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- arrival_date >  29.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 7.59] class: 1
|   |   |   |   |   |   |   |--- lead_time >  16.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 135.00
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_previous_bookings_not_canceled <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_previous_bookings_not_canceled >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [21.62, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  135.00
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 12.14] class: 1
|   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |--- weights: [1199.59, 1.52] class: 0
|   |   |   |   |   |--- avg_price_per_room >  196.50
|   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 63.29
|   |   |   |   |   |   |   |   |--- arrival_date <= 20.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [41.75, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  20.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 59.75
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 23.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.49, 12.14] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  23.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [14.91, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  59.75
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 44.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 59.21] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  44.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  63.29
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 3.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 59.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- lead_time >  59.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [20.13, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  3.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.75, 15.18] class: 1
|   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |--- weights: [413.04, 27.33] class: 0
|   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |--- avg_price_per_room <= 99.98
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 62.50
|   |   |   |   |   |   |   |   |   |--- weights: [15.66, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  62.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [8.20, 25.81] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |--- weights: [55.17, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 73.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  73.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [21.62, 4.55] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  99.98
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 132.43
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 122.97] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  132.43
|   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- lead_time <= 117.50
|   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |--- avg_price_per_room <= 75.07
|   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 58.75
|   |   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  58.75
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 118.41] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [31.31, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.96, 9.11] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  75.07
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [59.64, 3.04] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.49, 16.70] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 86.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 16.70] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  86.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [8.95, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [44.73, 4.55] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |--- weights: [16.40, 39.47] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |--- weights: [20.13, 6.07] class: 0
|   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 102.09
|   |   |   |   |   |   |   |   |--- weights: [5.22, 144.22] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  102.09
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 109.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 16.70] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [33.55, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  109.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 124.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.98, 75.91] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  124.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 3.04] class: 0
|   |   |   |   |--- lead_time >  117.50
|   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |--- arrival_date <= 7.50
|   |   |   |   |   |   |   |--- weights: [38.02, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_date >  7.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 65.38
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  65.38
|   |   |   |   |   |   |   |   |   |--- weights: [24.60, 3.04] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |   |   |--- arrival_date <= 28.00
|   |   |   |   |   |   |   |   |   |--- weights: [14.91, 72.87] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  28.00
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 1.52] class: 0
|   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |--- weights: [84.25, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |--- lead_time <= 125.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 90.85
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 87.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [13.42, 13.66] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  87.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 15.18] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  90.85
|   |   |   |   |   |   |   |   |   |--- weights: [10.44, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  125.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 19.50
|   |   |   |   |   |   |   |   |   |--- weights: [58.15, 18.22] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  19.50
|   |   |   |   |   |   |   |   |   |--- weights: [61.88, 1.52] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 13.50
|   |   |   |   |--- avg_price_per_room <= 99.44
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [92.45, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 70.05
|   |   |   |   |   |   |   |   |   |--- weights: [31.31, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  70.05
|   |   |   |   |   |   |   |   |   |--- lead_time <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [38.77, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |--- lead_time >  5.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [34.30, 40.99] class: 1
|   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 19.74] class: 1
|   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 2.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 74.21
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  74.21
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 10.63] class: 1
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [155.07, 6.07] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [3.73, 10.63] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [7.46, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  99.44
|   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |--- avg_price_per_room <= 202.67
|   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |--- weights: [63.37, 30.36] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 20.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [115.56, 12.14] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  20.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [28.33, 3.04] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 6.07] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  202.67
|   |   |   |   |   |   |   |--- weights: [0.75, 22.77] class: 1
|   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 119.25
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 118.50
|   |   |   |   |   |   |   |   |   |--- weights: [18.64, 59.21] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  118.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.20, 1.52] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  119.25
|   |   |   |   |   |   |   |   |--- weights: [34.30, 171.55] class: 1
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- weights: [26.09, 1.52] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 14.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 36.43] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  14.00
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 208.67
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  208.67
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [15.66, 0.00] class: 0
|   |   |   |--- lead_time >  13.50
|   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 71.92
|   |   |   |   |   |   |--- avg_price_per_room <= 59.43
|   |   |   |   |   |   |   |--- lead_time <= 84.50
|   |   |   |   |   |   |   |   |--- weights: [50.70, 7.59] class: 0
|   |   |   |   |   |   |   |--- lead_time >  84.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.00
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 131.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 15.18] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  131.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- weights: [10.44, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  59.43
|   |   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |   |--- weights: [20.88, 6.07] class: 0
|   |   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.34
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [15.66, 78.94] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 102.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  102.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.34
|   |   |   |   |   |   |   |   |   |--- weights: [11.18, 0.00] class: 0
|   |   |   |   |   |--- avg_price_per_room >  71.92
|   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |--- lead_time <= 65.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 120.45
|   |   |   |   |   |   |   |   |   |--- weights: [79.77, 9.11] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  120.45
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 12.14] class: 1
|   |   |   |   |   |   |   |--- lead_time >  65.50
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [16.40, 47.06] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 63.76] class: 1
|   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 104.31
|   |   |   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [16.40, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [38.77, 118.41] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [39.51, 185.21] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [73.81, 411.41] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  104.31
|   |   |   |   |   |   |   |   |--- arrival_month <= 10.50
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 195.30
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  195.30
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 138.15] class: 1
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 >  0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 9.11] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  10.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 168.06
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 22.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  22.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [17.15, 83.50] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  168.06
|   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 6.07] class: 0
|   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |--- weights: [48.46, 1.52] class: 0
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |--- lead_time <= 102.50
|   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |--- weights: [697.09, 9.11] class: 0
|   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |--- lead_time <= 63.00
|   |   |   |   |   |   |   |--- weights: [15.66, 1.52] class: 0
|   |   |   |   |   |   |--- lead_time >  63.00
|   |   |   |   |   |   |   |--- weights: [0.00, 7.59] class: 1
|   |   |   |   |--- lead_time >  102.50
|   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |--- lead_time <= 105.00
|   |   |   |   |   |   |   |--- weights: [0.75, 6.07] class: 1
|   |   |   |   |   |   |--- lead_time >  105.00
|   |   |   |   |   |   |   |--- weights: [31.31, 13.66] class: 0
|   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |--- weights: [44.73, 3.04] class: 0
|   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |--- lead_time <= 8.50
|   |   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |   |--- no_of_week_nights <= 10.00
|   |   |   |   |   |   |   |--- weights: [498.03, 40.99] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  10.00
|   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |   |--- arrival_date <= 13.50
|   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |--- weights: [58.90, 36.43] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |--- weights: [33.55, 1.52] class: 0
|   |   |   |   |   |   |--- arrival_date >  13.50
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [123.76, 9.11] class: 0
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 126.33
|   |   |   |   |   |   |   |   |   |--- weights: [32.80, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  126.33
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 13.66] class: 1
|   |   |   |   |--- lead_time >  8.50
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- avg_price_per_room <= 118.55
|   |   |   |   |   |   |   |--- lead_time <= 61.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [70.08, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [126.74, 1.52] class: 0
|   |   |   |   |   |   |   |--- lead_time >  61.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 57.69] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 66.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  66.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.93
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [54.43, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.93
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |--- avg_price_per_room >  118.55
|   |   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 19.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 177.15
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  177.15
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 6.07] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  19.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 121.20
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [18.64, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  121.20
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 55.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  55.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [11.93, 10.63] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [37.28, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 119.20
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 28.84] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  119.20
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [49.95, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 18.22] class: 1
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.20, 1.52] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- weights: [1585.04, 0.00] class: 0
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- no_of_week_nights <= 9.50
|   |   |   |   |   |   |   |--- lead_time <= 6.50
|   |   |   |   |   |   |   |   |--- weights: [32.06, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  6.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  5.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 93.09
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  93.09
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [77.54, 27.33] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [19.38, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  9.50
|   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [52.19, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |--- avg_price_per_room <= 202.95
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.49, 9.11] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.20, 3.04] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- lead_time <= 150.50
|   |   |   |   |   |   |   |   |   |--- weights: [175.20, 28.84] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  150.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  202.95
|   |   |   |   |   |   |   |--- weights: [0.00, 10.63] class: 1
|   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |--- avg_price_per_room <= 153.15
|   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 2 <= 0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.12
|   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.12
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 90.42
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 7.59] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  90.42
|   |   |   |   |   |   |   |   |   |   |--- weights: [64.12, 60.72] class: 0
|   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 2 >  0.50
|   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  153.15
|   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |--- weights: [67.10, 0.00] class: 0
|--- lead_time >  151.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- no_of_special_requests <= 0.50
|   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |--- lead_time <= 163.50
|   |   |   |   |   |   |--- arrival_month <= 5.00
|   |   |   |   |   |   |   |--- weights: [2.98, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  5.00
|   |   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |   |--- lead_time >  163.50
|   |   |   |   |   |   |--- lead_time <= 341.00
|   |   |   |   |   |   |   |--- lead_time <= 173.00
|   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |--- weights: [46.97, 9.11] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 13.66] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  173.00
|   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |--- weights: [188.62, 7.59] class: 0
|   |   |   |   |   |   |--- lead_time >  341.00
|   |   |   |   |   |   |   |--- weights: [13.42, 27.33] class: 1
|   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |--- avg_price_per_room <= 2.50
|   |   |   |   |   |   |--- lead_time <= 285.50
|   |   |   |   |   |   |   |--- weights: [8.20, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  285.50
|   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |--- avg_price_per_room >  2.50
|   |   |   |   |   |   |--- weights: [0.75, 97.16] class: 1
|   |   |   |--- no_of_adults >  1.50
|   |   |   |   |--- avg_price_per_room <= 82.47
|   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |--- weights: [2.98, 282.37] class: 1
|   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |--- lead_time <= 244.00
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 166.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  166.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 57.69] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [17.89, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 12.14] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [75.30, 12.14] class: 0
|   |   |   |   |   |   |   |--- lead_time >  244.00
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- weights: [25.35, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 80.38
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 264.15] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [7.46, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |--- weights: [46.22, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  82.47
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- lead_time <= 324.50
|   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [7.46, 986.78] class: 1
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 10.63] class: 1
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 19.74] class: 1
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  324.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 89.00
|   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  89.00
|   |   |   |   |   |   |   |   |--- weights: [0.75, 13.66] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |--- no_of_special_requests >  0.50
|   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- weights: [1.49, 7.59] class: 1
|   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |--- arrival_date <= 1.50
|   |   |   |   |   |   |   |--- weights: [1.49, 3.04] class: 1
|   |   |   |   |   |   |--- arrival_date >  1.50
|   |   |   |   |   |   |   |--- weights: [35.79, 1.52] class: 0
|   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |   |   |--- weights: [7.46, 206.46] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- avg_price_per_room <= 76.48
|   |   |   |   |   |   |   |--- weights: [46.97, 4.55] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  76.48
|   |   |   |   |   |   |   |--- no_of_week_nights <= 6.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 233.00
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 152.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.49, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  152.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- lead_time >  233.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 19.74] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 15.18] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 269.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  269.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  6.50
|   |   |   |   |   |   |   |   |--- weights: [4.47, 13.66] class: 1
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- arrival_date <= 14.50
|   |   |   |   |   |   |   |--- weights: [8.20, 3.04] class: 0
|   |   |   |   |   |   |--- arrival_date >  14.50
|   |   |   |   |   |   |   |--- weights: [11.18, 31.88] class: 1
|   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |--- lead_time <= 348.50
|   |   |   |   |   |   |--- weights: [106.61, 3.04] class: 0
|   |   |   |   |   |--- lead_time >  348.50
|   |   |   |   |   |   |--- weights: [5.96, 4.55] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- arrival_month <= 11.50
|   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |--- weights: [0.00, 3200.19] class: 1
|   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |--- arrival_month >  11.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- weights: [35.04, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |--- weights: [3.73, 22.77] class: 1


importances = best_model.feature_importances_ # get feature importances from the model
indices = np.argsort(importances) # sort feature importances by ascending order

plt.figure(figsize=(12, 12))
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color='violet', align='center') # plot horizontal bar chart of feature importances
plt.yticks(range(len(indices)), [feature_names[i] for i in indices]) # set y-axis as feature names sorted by importance
plt.xlabel('Relative Importance') # set x-axis label
plt.show()


# concatenate dataframes with training performance metrics
models_train_comp_df = pd.concat(
    [
        decision_tree_perf_train.T, # dataframe for Decision Tree sklearn
        decision_tree_tune_perf_train.T, # dataframe for Decision Tree (Pre-Pruning)
        decision_tree_post_perf_train.T, # dataframe for Decision Tree (Post-Pruning)
    ],
    axis=1,)

# set column names for concatenated dataframe
models_train_comp_df.columns = [
    'Decision Tree sklearn',
    'Decision Tree (Pre-Pruning)',
    'Decision Tree (Post-Pruning)',
]

# print dataframe with message indicating it shows training performance comparison
print('Training performance comparison:')
models_train_comp_df

Training performance comparison:


# concatenate dataframes with training performance metrics
models_test_comp_df = pd.concat(
    [
    decision_tree_perf_test.T, # dataframe for Decision Tree sklearn
    decision_tree_tune_perf_test.T, # dataframe for Decision Tree (Pre-Pruning)
    decision_tree_post_test.T, # dataframe for Decision Tree (Post-Pruning)
], 
axis=1)

# set column names for concatenated dataframe
models_test_comp_df.columns = [
    'Decision Tree sklearn',
    'Decision Tree (Pre-Pruning)',
    'Decision Tree (Post-Pruning)',
]

# print dataframe with message indicating it shows training performance comparison
print('Test set performance comparison:')
models_test_comp_df

Test set performance comparison:


# code to convert Jupyter notebook in Google Colab to html format for submission
%%shell
jupyter nbconvert --to html ///content/INNHotels_Kimberly_Magerl1.ipynb

[NbConvertApp] Converting notebook ///content/INNHotels_Kimberly_Magerl1.ipynb to html
[NbConvertApp] Writing 3144117 bytes to /content/INNHotels_Kimberly_Magerl1.html

	no_of_adults	no_of_children	no_of_weekend_nights	no_of_week_nights	required_car_parking_space	lead_time	arrival_year	arrival_month	arrival_date	repeated_guest	no_of_previous_cancellations	no_of_previous_bookings_not_canceled	avg_price_per_room	no_of_special_requests
count	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000	36275.00000
mean	1.84496	0.10528	0.81072	2.20430	0.03099	85.23256	2017.82043	7.42365	15.59700	0.02564	0.02335	0.15341	103.42354	0.61966
std	0.51871	0.40265	0.87064	1.41090	0.17328	85.93082	0.38384	3.06989	8.74045	0.15805	0.36833	1.75417	35.08942	0.78624
min	0.00000	0.00000	0.00000	0.00000	0.00000	0.00000	2017.00000	1.00000	1.00000	0.00000	0.00000	0.00000	0.00000	0.00000
25%	2.00000	0.00000	0.00000	1.00000	0.00000	17.00000	2018.00000	5.00000	8.00000	0.00000	0.00000	0.00000	80.30000	0.00000
50%	2.00000	0.00000	1.00000	2.00000	0.00000	57.00000	2018.00000	8.00000	16.00000	0.00000	0.00000	0.00000	99.45000	0.00000
75%	2.00000	0.00000	2.00000	3.00000	0.00000	126.00000	2018.00000	10.00000	23.00000	0.00000	0.00000	0.00000	120.00000	1.00000
max	4.00000	10.00000	7.00000	17.00000	1.00000	443.00000	2018.00000	12.00000	31.00000	1.00000	13.00000	58.00000	540.00000	5.00000

	no_of_adults	no_of_children	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	required_car_parking_space	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	repeated_guest	no_of_previous_cancellations	no_of_previous_bookings_not_canceled	avg_price_per_room	no_of_special_requests	booking_status
63	1	0	0	1	Meal Plan 1	0	Room_Type 1	2	2017	9	10	Complementary	0	0	0	0.00000	1	Not_Canceled
145	1	0	0	2	Meal Plan 1	0	Room_Type 1	13	2018	6	1	Complementary	1	3	5	0.00000	1	Not_Canceled
209	1	0	0	0	Meal Plan 1	0	Room_Type 1	4	2018	2	27	Complementary	0	0	0	0.00000	1	Not_Canceled
266	1	0	0	2	Meal Plan 1	0	Room_Type 1	1	2017	8	12	Complementary	1	0	1	0.00000	1	Not_Canceled
267	1	0	2	1	Meal Plan 1	0	Room_Type 1	4	2017	8	23	Complementary	0	0	0	0.00000	1	Not_Canceled
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
35983	1	0	0	1	Meal Plan 1	0	Room_Type 7	0	2018	6	7	Complementary	1	4	17	0.00000	1	Not_Canceled
36080	1	0	1	1	Meal Plan 1	0	Room_Type 7	0	2018	3	21	Complementary	1	3	15	0.00000	1	Not_Canceled
36114	1	0	0	1	Meal Plan 1	0	Room_Type 1	1	2018	3	2	Online	0	0	0	0.00000	0	Not_Canceled
36217	2	0	2	1	Meal Plan 1	0	Room_Type 2	3	2017	8	9	Online	0	0	0	0.00000	2	Not_Canceled
36250	1	0	0	2	Meal Plan 2	0	Room_Type 1	6	2017	12	10	Online	0	0	0	0.00000	0	Not_Canceled

	const	no_of_adults	no_of_children	no_of_weekend_nights	no_of_week_nights	required_car_parking_space	lead_time	arrival_year	arrival_month	repeated_guest	no_of_previous_cancellations	avg_price_per_room	no_of_special_requests	type_of_meal_plan_Meal Plan 2	type_of_meal_plan_Not Selected	room_type_reserved_Room_Type 2	room_type_reserved_Room_Type 4	room_type_reserved_Room_Type 5	room_type_reserved_Room_Type 6	room_type_reserved_Room_Type 7	market_segment_type_Corporate	market_segment_type_Offline
Odds	0.00000	1.11491	1.16546	1.11470	1.04258	0.20296	1.01583	1.57195	0.95839	0.06478	1.25712	1.01937	0.22996	1.17846	1.33109	0.70104	0.75364	0.47885	0.37977	0.23827	0.45326	0.16773
Change_odd%	-100.00000	11.49096	16.54593	11.46966	4.25841	-79.70395	1.58331	57.19508	-4.16120	-93.52180	25.71181	1.93684	-77.00374	17.84641	33.10947	-29.89588	-24.63551	-52.11548	-62.02290	-76.17294	-54.67373	-83.22724

	Logistic Regression-default Threshold	Logistic Regression-0.37 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.80545	0.79265	0.80132
Recall	0.63267	0.73622	0.69939
Precision	0.73907	0.66808	0.69797
F1	0.68174	0.70049	0.69868

	Logistic Regression-default Threshold	Logistic Regression-0.37 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.80345	0.79555	0.80345
Recall	0.70358	0.73964	0.70358
Precision	0.69353	0.66573	0.69353
F1	0.69852	0.70074	0.69852

	Booking_ID	no_of_adults	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
0	INN00001	2	1	2	Meal Plan 1	Room_Type 1	224	2017	10	2	Offline	65.00000	0	Not_Canceled
1	INN00002	2	2	3	Not Selected	Room_Type 1	5	2018	11	6	Online	106.68000	1	Not_Canceled
2	INN00003	1	2	1	Meal Plan 1	Room_Type 1	1	2018	2	28	Online	60.00000	0	Canceled
3	INN00004	2	0	2	Meal Plan 1	Room_Type 1	211	2018	5	20	Online	100.00000	0	Canceled
4	INN00005	2	1	1	Not Selected	Room_Type 1	48	2018	4	11	Online	94.50000	0	Canceled

	Booking_ID	no_of_adults	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
36270	INN36271	3	2	6	Meal Plan 1	Room_Type 4	85	2018	8	3	Online	167.80000	1	Not_Canceled
36271	INN36272	2	1	3	Meal Plan 1	Room_Type 1	228	2018	10	17	Online	90.95000	2	Canceled
36272	INN36273	2	2	6	Meal Plan 1	Room_Type 1	148	2018	7	1	Online	98.39000	2	Not_Canceled
36273	INN36274	2	0	3	Not Selected	Room_Type 1	63	2018	4	21	Online	94.50000	0	Canceled
36274	INN36275	2	1	2	Meal Plan 1	Room_Type 1	207	2018	12	30	Offline	161.67000	0	Not_Canceled

	type_of_meal_plan	room_type_reserved	market_segment_type	booking_status
count	36275	36275	36275	36275
unique	4	7	5	2
top	Meal Plan 1	Room_Type 1	Online	Not_Canceled
freq	27835	28130	23214	24390

	feature	VIF
0	const	39497686.20788
1	no_of_adults	1.35113
2	no_of_children	2.09358
3	no_of_weekend_nights	1.06948
4	no_of_week_nights	1.09571
5	required_car_parking_space	1.03997
6	lead_time	1.39517
7	arrival_year	1.43190
8	arrival_month	1.27633
9	arrival_date	1.00679
10	repeated_guest	1.78358
11	no_of_previous_cancellations	1.39569
12	no_of_previous_bookings_not_canceled	1.65200
13	avg_price_per_room	2.06860
14	no_of_special_requests	1.24798
15	type_of_meal_plan_Meal Plan 2	1.27328
16	type_of_meal_plan_Meal Plan 3	1.02526
17	type_of_meal_plan_Not Selected	1.27306
18	room_type_reserved_Room_Type 2	1.10595
19	room_type_reserved_Room_Type 3	1.00330
20	room_type_reserved_Room_Type 4	1.36361
21	room_type_reserved_Room_Type 5	1.02800
22	room_type_reserved_Room_Type 6	2.05614
23	room_type_reserved_Room_Type 7	1.11816
24	market_segment_type_Complementary	4.50276
25	market_segment_type_Corporate	16.92829
26	market_segment_type_Offline	64.11564
27	market_segment_type_Online	71.18026

	ccp_alphas	impurities
0	0.00000	0.00838
1	0.00000	0.00838
2	0.00000	0.00838
3	0.00000	0.00838
4	0.00000	0.00838
...	...	...
1839	0.00890	0.32806
1840	0.00980	0.33786
1841	0.01272	0.35058
1842	0.03412	0.41882
1843	0.08118	0.50000

	Decision Tree sklearn	Decision Tree (Pre-Pruning)	Decision Tree (Post-Pruning)
Accuracy	0.99421	0.83097	0.89954
Recall	0.98661	0.78608	0.90303
Precision	0.99578	0.72425	0.81274
F1	0.99117	0.75390	0.85551

	Decision Tree sklearn	Decision Tree (Pre-Pruning)	Decision Tree (Post-Pruning)
Accuracy	0.87118	0.83497	0.86879
Recall	0.81175	0.78336	0.85576
Precision	0.79461	0.72758	0.76614
F1	0.80309	0.75444	0.80848

INN Hotels Project¶

Context¶

Objective¶

Data Description¶

Import Libraries¶

Load the Data Set¶

Data Overview¶

Observations¶

Observations¶

Observations¶

Observations¶

Exploratory Data Analysis (EDA)¶

Observations¶

Observations¶

Univariate Analysis¶

Observations on Lead Time¶

Observations¶

Observations on Average Price Per Room¶

Observations¶

Observations¶

Observations¶

Observations¶

Observation¶

Observations on Previous Cancellations¶

Observations¶

Observations on Previous Booking Not Canceled¶

Observations¶

Observations on Number of Children¶

Observations¶

Observations¶

Observations on Number of Adults¶

Observations¶

Observations on Number of Weekend Nights¶

Observations¶

Observations on Number of Week Nights¶

Observations¶

Observations on Reserved Room Type¶

Observations¶

Observations on Required Car Parking Space¶

Observations¶

Observations on Type of Meal Plan¶

Observations¶

Observations on Arrival Month¶

Observations¶

Observations on Market Segment Type¶

Observations¶

Observations on Booking Status¶

Observations¶

Observations on Number of Special Requests¶

Observations¶

Bivariate Analysis¶

Observations¶

Q1: What are the busiest months in the hotel?¶

Observations¶

Q2: Which market segment do most of the guests come from?¶

Observations¶

Q3: Hotel rates are dynamic and change according to demand and customer demographics. What are the differences in room prices in different market segments?¶

Observations¶

Q4: How does booking status vary across market segments?¶

Observations¶

Q5: What percentage of bookings are canceled?¶

Observations¶

Q6: Repeating guests are the guests who stay in the hotel often and are important to brand equity. What percentage of repeating guests cancel?¶

Observations¶

Q7: Many guests have special requirements when booking a hotel room. Do these requirements affect booking cancellation?¶

Observations¶

Q8: Do special requests impact price?¶

Observations¶

Q9: Analyze the positive correlation between booking status and the average price per room.¶

Observations¶

Q10: Analyze the positive correlation between booking status and lead time.¶

Observations¶

Q11: What is the busiest month in the hotel?¶

Observations¶

Q12: How does the price vary across different months?¶

Observations¶

Data Preprocessing¶

Outlier Detection¶

Observations¶

Model Building¶